-
公开(公告)号：US07805017B1
公开(公告)日：2010-09-28
申请号：US11745826
申请日：2007-05-08
Applicant: Andrea Basso , Eric Cosatto , David Crawford Gibbon , Hans Peter Graf , Shan Liu
Inventor： Andrea Basso , Eric Cosatto , David Crawford Gibbon , Hans Peter Graf , Shan Liu
CPC classification number: G06K9/00281 , G06F3/012 , G06K9/00228 , G06K9/2027 , G06T7/246 , G06T15/50 , G06T17/00 , G06T2200/08 , G06T2207/10152 , G06T2207/30201 , H04N7/147 , H04N7/15
Abstract: A method of improving the lighting conditions of a real scene or video sequence. Digitally generated light is added to a scene for video conferencing over telecommunication networks. A virtual illumination equation takes into account light attenuation, lambertian and specular reflection. An image of an object is captured, a virtual light source illuminates the object within the image. In addition, the object can be the head of the user. The position of the head of the user is dynamically tracked so that an three-dimensional model is generated which is representative of the head of the user. Synthetic light is applied to a position on the model to form an illuminated model.
Abstract translation: 一种改善真实场景或视频序列的照明条件的方法。 数字生成的光被添加到通过电信网络进行视频会议的场景中。 虚拟照明方程考虑了光衰减，朗伯和镜面反射。 捕获对象的图像，虚拟光源照亮图像内的对象。 另外，对象可以是用户的头。 动态跟踪用户头部的位置，从而生成代表用户头部的三维模型。 将合成光应用于模型上的位置以形成照明模型。
-
公开(公告)号：US20100172568A1
公开(公告)日：2010-07-08
申请号：US12496795
申请日：2009-07-02
Applicant: Christopher Malon , Matthew L. Miller , Eric Cosatto
Inventor： Christopher Malon , Matthew L. Miller , Eric Cosatto
CPC classification number: G06K9/00147 , G01N1/312 , G06T7/0012 , G06T2207/20061 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: A detector and method for automatically detecting signet ring cells in an image of a biopsy tissue sample, includes finding in the image, points about which cell membranes appear in radial symmetry; selecting as candidate points, at least ones of the points that have an adjacent nuclei with a predetermined shape feature; and applying a convolutional neural network to the candidate points to determine which of the candidate points are signet ring cells.
Abstract translation: 用于在活检组织样本的图像中自动检测印戒细胞的检测器和方法包括在图像中发现关于哪个细胞膜呈径向对称的点; 选择候选点，具有具有预定形状特征的相邻核的点中的至少一个; 以及向所述候选点应用卷积神经网络，以确定所述候选点中的哪一个是所述环形蜂窝小区。
-
33.发明申请System and Method for Parallelizing and Accelerating Learning Machine Training and Classification Using a Massively Parallel Accelerator 有权使用大规模并行加速器并行和加速学习机器训练和分类的系统和方法公开(公告)号：US20090304268A1
公开(公告)日：2009-12-10
申请号：US12478073
申请日：2009-06-04
Applicant: Srihari Cadambi , Igor Durdanovic , Venkata Jakkula , Eric Cosatto , Murugan Sankaradass , Hans Peter Graf , Srimat T. Chakradhar
Inventor： Srihari Cadambi , Igor Durdanovic , Venkata Jakkula , Eric Cosatto , Murugan Sankaradass , Hans Peter Graf , Srimat T. Chakradhar
CPC classification number: G06N99/005
Abstract: A method system for training an apparatus to recognize a pattern includes providing the apparatus with a host processor executing steps of a machine learning process; providing the apparatus with an accelerator including at least two processors; inputting training pattern data into the host processor; determining coefficient changes in the machine learning process with the host processor using the training pattern data; transferring the training data to the accelerator; determining kernel dot-products with the at least two processors of the accelerator using the training data; and transferring the dot-products back to the host processor.
Abstract translation: 用于训练识别模式的装置的方法系统包括向所述装置提供执行机器学习过程的步骤的主机处理器; 向所述设备提供包括至少两个处理器的加速器; 将训练模式数据输入到主处理器中; 使用所述训练模式数据来确定主处理器在机器学习过程中的系数变化; 将训练数据传送到加速器; 使用所述训练数据确定具有所述加速器的所述至少两个处理器的内核点产品; 并将点产品传送回主机处理器。
-
公开(公告)号：US20080201281A1
公开(公告)日：2008-08-21
申请号：US12110519
申请日：2008-04-28
Applicant: Hans Peter Graf , Eric Cosatto , Leon Bottou , Vladimir N. Vapnik
Inventor： Hans Peter Graf , Eric Cosatto , Leon Bottou , Vladimir N. Vapnik
IPC: G06F15/18
CPC classification number: G06K9/6292 , G06K9/6269 , G06N99/005
Abstract: Disclosed is an improved technique for training a support vector machine using a distributed architecture. A training data set is divided into subsets, and the subsets are optimized in a first level of optimizations, with each optimization generating a support vector set. The support vector sets output from the first level optimizations are then combined and used as input to a second level of optimizations. This hierarchical processing continues for multiple levels, with the output of each prior level being fed into the next level of optimizations. In order to guarantee a global optimal solution, a final set of support vectors from a final level of optimization processing may be fed back into the first level of the optimization cascade so that the results may be processed along with each of the training data subsets. This feedback may continue in multiple iterations until the same final support vector set is generated during two sequential iterations through the cascade, thereby guaranteeing that the solution has converged to the global optimal solution. In various embodiments, various combinations of inputs may be used by the various optimizations. The individual optimizations may be processed in parallel.
Abstract translation: 公开了一种用于使用分布式架构来训练支持向量机的改进技术。 将训练数据集分为子集，并且子集在优化的第一级优化，每个优化生成支持向量集。 然后将来自第一级优化的支持向量集合输出组合并用作第二级优化的输入。 该分级处理持续多级，每个先前级别的输出被馈送到下一级优化。 为了保证全局最优解，可以将最终优化处理级别的最后一组支持向量反馈到优化级联的第一级，以便结果可以与每个训练数据子集一起被处理。 这种反馈可以在多次迭代中继续，直到在通过级联的两次连续迭代期间产生相同的最终支持向量集，从而保证解已经收敛到全局最优解。 在各种实施例中，各种优化可以使用输入的各种组合。 个别优化可以并行处理。
-
公开(公告)号：US07260539B2
公开(公告)日：2007-08-21
申请号：US10423789
申请日：2003-04-25
Applicant: Eric Cosatto , Hans Peter Graf , Joern Ostermann
Inventor： Eric Cosatto , Hans Peter Graf , Joern Ostermann
IPC: G10L21/00
CPC classification number: G06F17/30905
Abstract: Methods and apparatus for rendering a talking head on a client device are disclosed. The client device has a client cache capable of storing audio/visual data associated with rendering the talking head. The method comprises storing sentences in a client cache of a client device that relate to bridging delays in a dialog, storing sentence templates to be used in dialogs, generating a talking head response to a user inquiry from the client device, and determining whether sentences or stored templates stored in the client cache relate to the talking head response. If the stored sentences or stored templates relate to the talking head response, the method comprises instructing the client device to use the appropriate stored sentence or template from the client cache to render at least a part of the talking head response and transmitting a portion of the talking head response not stored in the client cache, if any, to the client device to render a complete talking head response. If the client cache has no stored data associated with the talking head response, the method comprises transmitting the talking head response to be rendered on the client device.
Abstract translation: 公开了一种用于在客户端设备上呈现通话头的方法和设备。 客户端设备具有能够存储与呈现话音头相关联的音频/视频数据的客户端高速缓存。 该方法包括将客户端设备的客户端缓存中的句子存储在与对话中的桥接延迟相关联，存储要在对话中使用的语句模板，从客户端设备生成对用户的询问头响应，以及确定句子或 存储在客户端缓存中的存储模板涉及到通话头响应。 如果存储的句子或存储的模板与谈话头响应相关，则该方法包括指示客户端设备使用来自客户端高速缓存的适当存储的句子或模板来呈现至少一部分通话头响应并且传送一部分 说话头响应没有存储在客户端缓存中（如果有的话）给客户端设备呈现完整的通话头响应。 如果客户端缓存没有与通话头响应相关联的存储数据，则该方法包括传送要在客户端设备上呈现的通话头响应。
-
Patent Agency Ranking
公开(公告)号：US5647027A
公开(公告)日：1997-07-08
申请号：US330885
申请日：1994-10-28
Applicant: Christopher John Burges , Eric Cosatto , Hans Peter Graf
Inventor： Christopher John Burges , Eric Cosatto , Hans Peter Graf
CPC classification number: G06K9/346 , G06K2209/01
Abstract: Noisy images of graphical or pictorial records, such as hand-written postal addresses, are cleaned by a method of analyzing the shapes of pixel clusters. According to such method, a set of structuring kernels is used to extract primitive shapes. The outcome of this extraction process is used to determine whether each pixel, in turn, is to be treated as part of a image element such as an alphanumeric character.
Abstract translation: 通过分析像素簇的形状的方法来清除图形或图形记录的嘈杂图像，例如手写邮政地址。 根据这种方法，使用一组结构化内核来提取原始形状。 该提取处理的结果用于确定每个像素是否被视为诸如字母数字字符的图像元素的一部分。
-
37.发明授权System and method for triphone-based unit selection for visual speech synthesis 有权用于视觉语音合成的基于耳机的单元选择的系统和方法公开(公告)号：US09583098B1
公开(公告)日：2017-02-28
申请号：US11924025
申请日：2007-10-25
Applicant: Eric Cosatto , Hans Peter Graf , Fu Jie Huang
Inventor： Eric Cosatto , Hans Peter Graf , Fu Jie Huang
CPC classification number: G10L15/08 , G10L13/07 , G10L15/26 , G10L2021/105 , H04N19/00
Abstract: A system and method for generating a video sequence having mouth movements synchronized with speech sounds are disclosed. The system utilizes a database of n-phones as the smallest selectable unit, wherein n is larger than 1 and preferably 3. The system calculates a target cost for each candidate n-phone for a target frame using a phonetic distance, coarticulation parameter, and speech rate. For each n-phone in a target sequence, the system searches for candidate n-phones that are visually similar according to the target cost. The system samples each candidate n-phone to get a same number of frames as in the target sequence and builds a video frame lattice of candidate video frames. The system assigns a joint cost to each pair of adjacent frames and searches the video frame lattice to construct the video sequence by finding the optimal path through the lattice according to the minimum of the sum of the target cost and the joint cost over the sequence.
Abstract translation: 公开了一种用于产生具有与语音的同步的口部动作的视频序列的系统和方法。 该系统利用n电话的数据库作为最小的可选单元，其中n大于1，并且优选地为3.系统使用语音距离，协调参数和目标帧来计算目标帧的每个候选n电话的目标成本 言语速度 对于目标序列中的每个n电话，系统根据目标成本搜索视觉上类似的候选n电话。 系统对每个候选n电话进行采样，以获得与目标序列相同数量的帧，并建立候选视频帧的视频帧格点。 系统为每对相邻帧分配联合成本，并通过根据目标成本和序列中的联合成本的总和的最小值找到通过网格的最优路径来搜索视频帧格以构建视频序列。
-
公开(公告)号：US08538161B2
公开(公告)日：2013-09-17
申请号：US13315487
申请日：2011-12-09
Applicant: Christopher Malon , Eric Cosatto
Inventor： Christopher Malon , Eric Cosatto
IPC: G06K9/46
CPC classification number: G06T7/0012 , G06K9/00127 , G06T7/12 , G06T2207/30024
Abstract: Systems and methods for extracting a radial contour around a given point in an image includes providing an image including a point about which a radial contour is to be extracted around. A plurality of directions around the point and a plurality of radius lengths for each direction are provided. Local costs are determined for all radius lengths for each direction by comparing texture variances at each radius length with the texture variance at a further radius length. A radius length is determined, using a processor, for each direction based on the accumulated value of the local costs to provide a radial contour.
Abstract translation: 用于提取图像中的给定点周围的径向轮廓的系统和方法包括提供包括要围绕其提取径向轮廓的点的图像。 提供了围绕该点的多个方向和每个方向的多个半径长度。 通过将每个半径长度处的纹理方差与另一半径长度上的纹理方差进行比较，确定每个方向的所有半径长度的局部花费。 使用处理器，根据本地成本的累积值来确定每个方向的半径长度以提供径向轮廓。
-
公开(公告)号：US08135652B2
公开(公告)日：2012-03-13
申请号：US12110519
申请日：2008-04-28
Applicant: Hans Peter Graf , Eric Cosatto , Leon Bottou , Vladimir N. Vapnik
Inventor： Hans Peter Graf , Eric Cosatto , Leon Bottou , Vladimir N. Vapnik
IPC: G06F15/18
CPC classification number: G06K9/6292 , G06K9/6269 , G06N99/005
Abstract: Disclosed is an improved technique for training a support vector machine using a distributed architecture. A training data set is divided into subsets, and the subsets are optimized in a first level of optimizations, with each optimization generating a support vector set. The support vector sets output from the first level optimizations are then combined and used as input to a second level of optimizations. This hierarchical processing continues for multiple levels, with the output of each prior level being fed into the next level of optimizations. In order to guarantee a global optimal solution, a final set of support vectors from a final level of optimization processing may be fed back into the first level of the optimization cascade so that the results may be processed along with each of the training data subsets. This feedback may continue in multiple iterations until the same final support vector set is generated during two sequential iterations through the cascade, thereby guaranteeing that the solution has converged to the global optimal solution. In various embodiments, various combinations of inputs may be used by the various optimizations. The individual optimizations may be processed in parallel.
Abstract translation: 公开了一种用于使用分布式架构来训练支持向量机的改进技术。 将训练数据集分为子集，并且子集在优化的第一级优化，每个优化生成支持向量集。 然后将来自第一级优化的支持向量集合输出组合并用作第二级优化的输入。 该分级处理持续多级，每个先前级别的输出被馈送到下一级优化。 为了保证全局最优解，可以将最终优化处理级别的最后一组支持向量反馈到优化级联的第一级，以便结果可以与每个训练数据子集一起被处理。 这种反馈可以在多次迭代中继续，直到在通过级联的两次连续迭代期间产生相同的最终支持向量集，从而保证解已经收敛到全局最优解。 在各种实施例中，各种优化可以使用输入的各种组合。 个别优化可以并行处理。
-
40.发明授权System and method of providing conversational visual prosody for talking heads 有权提供谈话头脑的会话视觉韵律的系统和方法公开(公告)号：US08131551B1
公开(公告)日：2012-03-06
申请号：US11458282
申请日：2006-07-18
Applicant: Eric Cosatto , Hans Peter Graf , Volker Franz Strom
Inventor： Eric Cosatto , Hans Peter Graf , Volker Franz Strom
IPC: G10L11/00
CPC classification number: G10L15/1807 , G10L2021/105
Abstract: A system and method of controlling the movement of a virtual agent while the agent is speaking to a human user during a conversation is disclosed. The method comprises receiving speech data to be spoken by the virtual agent, performing a prosodic analysis of the speech data, selecting matching prosody patterns from a speaking database and controlling the virtual agent movement according to the selected prosody patterns.
Abstract translation: 公开了一种系统和方法，用于在对话期间代理人与人类用户对话时控制虚拟代理的移动。 该方法包括：接收由虚拟代理人发言的语音数据，执行语音数据的韵律分析，从说话数据库中选择匹配韵律模式，并根据所选择的韵律模式控制虚拟代理的移动。
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.015 seconds)
